Boshu Ru
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Boshu Ru has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Amar K. Das
Guardant Health Inc
3 shared publications - Lixia Yao
Department of Health Sciences Research, Mayo Clinic, Rochester, MN, United States
3 shared publications - Manjiri Pawaskar
Merck & Co., Inc, Merck Research Laboratories (MRL), Rahway, USA
3 shared publications - Nelson Lee Afanador
Merck & Co, Inc Rahway, NJ United States
3 shared publications - Richard Baumgartner
Merck & Co., Inc., Rahway, New Jersey, USA
3 shared publications - Stephanie A. Kujawski
Department of Epidemiology, Mailman School of Public Health, Columbia University, New York, New York, United States of America
3 shared publications
Latest Publications
- Open Access
- 20 August 2025
- Published by Elsevier in Journal of Cardiac Failure
- Vol. 32 (7) , 1153-1161
Characterizing real-world use of vericiguat in the United States
- 20 August 2025
- Published by Elsevier in Journal of Cardiac Failure
- Vol. 32 (7) , 1153-1161
Open AccessCharacterizing real-world use of vericiguat in the United States
- Open Access
- 6 March 2024
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 12 (1) , e47744
Real-World Data Quality Framework for Oncology Time to Treatment Discontinuation Use Case: Implementation and Evaluation Study
Background: The importance of real-world evidence is widely recognized in observational oncology studies. However, the lack of interoperable data quality standards in the fragmented health information technology landscape represents an important challenge. Therefore, adopting validated systematic methods for evaluating data quality is important for oncology outcomes research leveraging real-world data (RWD). Objective: This study aims to implement real-world time to treatment discontinuation (rwTTD) for a systemic anticancer therapy (SACT) as a new use case for the Use Case Specific Relevance and Quality Assessment, a framework linking data quality and relevance in fit-for-purpose RWD assessment. Methods: To define the rwTTD use case, we mapped the operational definition of rwTTD to RWD elements commonly available from oncology electronic health record–derived data sets. We identified 20 tasks to check the completeness and plausibility of data elements concerning SACT use, line of therapy (LOT), death date, and length of follow-up. Using descriptive statistics, we illustrated how to implement the Use Case Specific Relevance and Quality Assessment on 2 oncology databases (Data sets A and B) to estimate the rwTTD of an SACT drug (target SACT) for patients with advanced head and neck cancer diagnosed on or after January 1, 2015. Results: A total of 1200 (24.96%) of 4808 patients in Data set A and 237 (5.92%) of 4003 patients in Data set B received the target SACT, suggesting better relevance of the former in estimating the rwTTD of the target SACT. The 2 data sets differed with regard to the terminology used for SACT drugs, LOT format, and target SACT LOT distribution over time. Data set B appeared to have less complete SACT records, longer lags in incorporating the latest data, and incomplete mortality data, suggesting a lack of fitness for estimating rwTTD. Conclusions: The fit-for-purpose data quality assessment demonstrated substantial variability in the quality of the 2 real-world data sets. The data quality specifications applied for rwTTD estimation can be expanded to support a broad spectrum of oncology use cases.
- 6 March 2024
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 12 (1) , e47744
Open AccessReal-World Data Quality Framework for Oncology Time to Treatment Discontinuation Use Case: Implementation and Evaluation Study
Background: The importance of real-world evidence is widely recognized in observational oncology studies. However, the lack of interoperable data quality standards in the fragmented health information technology landscape represents an important challenge. Therefore, adopting validated systematic methods for evaluating data quality is important for oncology outcomes research leveraging real-world data (RWD). Objective: This study aims to implement real-world time to treatment discontinuation (rwTTD) for a systemic anticancer therapy (SACT) as a new use case for the Use Case Specific Relevance and Quality Assessment, a framework linking data quality and relevance in fit-for-purpose RWD assessment. Methods: To define the rwTTD use case, we mapped the operational definition of rwTTD to RWD elements commonly available from oncology electronic health record–derived data sets. We identified 20 tasks to check the completeness and plausibility of data elements concerning SACT use, line of therapy (LOT), death date, and length of follow-up. Using descriptive statistics, we illustrated how to implement the Use Case Specific Relevance and Quality Assessment on 2 oncology databases (Data sets A and B) to estimate the rwTTD of an SACT drug (target SACT) for patients with advanced head and neck cancer diagnosed on or after January 1, 2015. Results: A total of 1200 (24.96%) of 4808 patients in Data set A and 237 (5.92%) of 4003 patients in Data set B received the target SACT, suggesting better relevance of the former in estimating the rwTTD of the target SACT. The 2 data sets differed with regard to the terminology used for SACT drugs, LOT format, and target SACT LOT distribution over time. Data set B appeared to have less complete SACT records, longer lags in incorporating the latest data, and incomplete mortality data, suggesting a lack of fitness for estimating rwTTD. Conclusions: The fit-for-purpose data quality assessment demonstrated substantial variability in the quality of the 2 real-world data sets. The data quality specifications applied for rwTTD estimation can be expanded to support a broad spectrum of oncology use cases.
- Open Access
- 17 April 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7 (1) , e41775
Comparison of Machine Learning Algorithms for Predicting Hospital Readmissions and Worsening Heart Failure Events in Patients With Heart Failure With Reduced Ejection Fraction: Modeling Study
Background: Heart failure (HF) is highly prevalent in the United States. Approximately one-third to one-half of HF cases are categorized as HF with reduced ejection fraction (HFrEF). Patients with HFrEF are at risk of worsening HF, have a high risk of adverse outcomes, and experience higher health care use and costs. Therefore, it is crucial to identify patients with HFrEF who are at high risk of subsequent events after HF hospitalization. Objective: Machine learning (ML) has been used to predict HF-related outcomes. The objective of this study was to compare different ML prediction models and feature construction methods to predict 30-, 90-, and 365-day hospital readmissions and worsening HF events (WHFEs). Methods: We used the Veradigm PINNACLE outpatient registry linked to Symphony Health’s Integrated Dataverse data from July 1, 2013, to September 30, 2017. Adults with a confirmed diagnosis of HFrEF and HF-related hospitalization were included. WHFEs were defined as HF-related hospitalizations or outpatient intravenous diuretic use within 1 year of the first HF hospitalization. We used different approaches to construct ML features from clinical codes, including frequencies of clinical classification software (CCS) categories, Bidirectional Encoder Representations From Transformers (BERT) trained with CCS sequences (BERT + CCS), BERT trained on raw clinical codes (BERT + raw), and prespecified features based on clinical knowledge. A multilayer perceptron neural network, extreme gradient boosting (XGBoost), random forest, and logistic regression prediction models were applied and compared. Results: A total of 30,687 adult patients with HFrEF were included in the analysis; 11.41% (3184/27,917) of adults experienced a hospital readmission within 30 days of their first HF hospitalization, and nearly half (9231/21,562, 42.81%) of the patients experienced at least 1 WHFE within 1 year after HF hospitalization. The prediction models and feature combinations with the best area under the receiver operating characteristic curve (AUC) for each outcome were XGBoost with CCS frequency (AUC=0.595) for 30-day readmission, random forest with CCS frequency (AUC=0.630) for 90-day readmission, XGBoost with CCS frequency (AUC=0.649) for 365-day readmission, and XGBoost with CCS frequency (AUC=0.640) for WHFEs. Our ML models could discriminate between readmission and WHFE among patients with HFrEF. Our model performance was mediocre, especially for the 30-day readmission events, most likely owing to limitations of the data, including an imbalance between positive and negative cases and high missing rates of many clinical variables and outcome definitions. Conclusions: We predicted readmissions and WHFEs after HF hospitalizations in patients with HFrEF. Features identified by data-driven approaches may be comparable with those identified by clinical domain knowledge. Future work may be warranted to validate and improve the models using more longitudinal electronic health records that are complete, are comprehensive, and have a longer follow-up time.
- 17 April 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7 (1) , e41775
Open AccessComparison of Machine Learning Algorithms for Predicting Hospital Readmissions and Worsening Heart Failure Events in Patients With Heart Failure With Reduced Ejection Fraction: Modeling Study
Background: Heart failure (HF) is highly prevalent in the United States. Approximately one-third to one-half of HF cases are categorized as HF with reduced ejection fraction (HFrEF). Patients with HFrEF are at risk of worsening HF, have a high risk of adverse outcomes, and experience higher health care use and costs. Therefore, it is crucial to identify patients with HFrEF who are at high risk of subsequent events after HF hospitalization. Objective: Machine learning (ML) has been used to predict HF-related outcomes. The objective of this study was to compare different ML prediction models and feature construction methods to predict 30-, 90-, and 365-day hospital readmissions and worsening HF events (WHFEs). Methods: We used the Veradigm PINNACLE outpatient registry linked to Symphony Health’s Integrated Dataverse data from July 1, 2013, to September 30, 2017. Adults with a confirmed diagnosis of HFrEF and HF-related hospitalization were included. WHFEs were defined as HF-related hospitalizations or outpatient intravenous diuretic use within 1 year of the first HF hospitalization. We used different approaches to construct ML features from clinical codes, including frequencies of clinical classification software (CCS) categories, Bidirectional Encoder Representations From Transformers (BERT) trained with CCS sequences (BERT + CCS), BERT trained on raw clinical codes (BERT + raw), and prespecified features based on clinical knowledge. A multilayer perceptron neural network, extreme gradient boosting (XGBoost), random forest, and logistic regression prediction models were applied and compared. Results: A total of 30,687 adult patients with HFrEF were included in the analysis; 11.41% (3184/27,917) of adults experienced a hospital readmission within 30 days of their first HF hospitalization, and nearly half (9231/21,562, 42.81%) of the patients experienced at least 1 WHFE within 1 year after HF hospitalization. The prediction models and feature combinations with the best area under the receiver operating characteristic curve (AUC) for each outcome were XGBoost with CCS frequency (AUC=0.595) for 30-day readmission, random forest with CCS frequency (AUC=0.630) for 90-day readmission, XGBoost with CCS frequency (AUC=0.649) for 365-day readmission, and XGBoost with CCS frequency (AUC=0.640) for WHFEs. Our ML models could discriminate between readmission and WHFE among patients with HFrEF. Our model performance was mediocre, especially for the 30-day readmission events, most likely owing to limitations of the data, including an imbalance between positive and negative cases and high missing rates of many clinical variables and outcome definitions. Conclusions: We predicted readmissions and WHFEs after HF hospitalizations in patients with HFrEF. Features identified by data-driven approaches may be comparable with those identified by clinical domain knowledge. Future work may be warranted to validate and improve the models using more longitudinal electronic health records that are complete, are comprehensive, and have a longer follow-up time.
- Open Access
- 4 April 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7 (1) , e42832
Predicting Measles Outbreaks in the United States: Evaluation of Machine Learning Approaches
Background: Measles, a highly contagious viral infection, is resurging in the United States, driven by international importation and declining domestic vaccination coverage. Despite this resurgence, measles outbreaks are still rare events that are difficult to predict. Improved methods to predict outbreaks at the county level would facilitate the optimal allocation of public health resources. Objective: We aimed to validate and compare extreme gradient boosting (XGBoost) and logistic regression, 2 supervised learning approaches, to predict the US counties most likely to experience measles cases. We also aimed to assess the performance of hybrid versions of these models that incorporated additional predictors generated by 2 clustering algorithms, hierarchical density-based spatial clustering of applications with noise (HDBSCAN) and unsupervised random forest (uRF). Methods: We constructed a supervised machine learning model based on XGBoost and unsupervised models based on HDBSCAN and uRF. The unsupervised models were used to investigate clustering patterns among counties with measles outbreaks; these clustering data were also incorporated into hybrid XGBoost models as additional input variables. The machine learning models were then compared to logistic regression models with and without input from the unsupervised models. Results: Both HDBSCAN and uRF identified clusters that included a high percentage of counties with measles outbreaks. XGBoost and XGBoost hybrid models outperformed logistic regression and logistic regression hybrid models, with the area under the receiver operating curve values of 0.920-0.926 versus 0.900-0.908, the area under the precision-recall curve values of 0.522-0.532 versus 0.485-0.513, and F2 scores of 0.595-0.601 versus 0.385-0.426. Logistic regression or logistic regression hybrid models had higher sensitivity than XGBoost or XGBoost hybrid models (0.837-0.857 vs 0.704-0.735) but a lower positive predictive value (0.122-0.141 vs 0.340-0.367) and specificity (0.793-0.821 vs 0.952-0.958). The hybrid versions of the logistic regression and XGBoost models had slightly higher areas under the precision-recall curve, specificity, and positive predictive values than the respective models that did not include any unsupervised features. Conclusions: XGBoost provided more accurate predictions of measles cases at the county level compared with logistic regression. The threshold of prediction in this model can be adjusted to align with each county’s resources, priorities, and risk for measles. While clustering pattern data from unsupervised machine learning approaches improved some aspects of model performance in this imbalanced data set, the optimal approach for the integration of such approaches with supervised machine learning models requires further investigation.
- 4 April 2023
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 7 (1) , e42832
Open AccessPredicting Measles Outbreaks in the United States: Evaluation of Machine Learning Approaches
Background: Measles, a highly contagious viral infection, is resurging in the United States, driven by international importation and declining domestic vaccination coverage. Despite this resurgence, measles outbreaks are still rare events that are difficult to predict. Improved methods to predict outbreaks at the county level would facilitate the optimal allocation of public health resources. Objective: We aimed to validate and compare extreme gradient boosting (XGBoost) and logistic regression, 2 supervised learning approaches, to predict the US counties most likely to experience measles cases. We also aimed to assess the performance of hybrid versions of these models that incorporated additional predictors generated by 2 clustering algorithms, hierarchical density-based spatial clustering of applications with noise (HDBSCAN) and unsupervised random forest (uRF). Methods: We constructed a supervised machine learning model based on XGBoost and unsupervised models based on HDBSCAN and uRF. The unsupervised models were used to investigate clustering patterns among counties with measles outbreaks; these clustering data were also incorporated into hybrid XGBoost models as additional input variables. The machine learning models were then compared to logistic regression models with and without input from the unsupervised models. Results: Both HDBSCAN and uRF identified clusters that included a high percentage of counties with measles outbreaks. XGBoost and XGBoost hybrid models outperformed logistic regression and logistic regression hybrid models, with the area under the receiver operating curve values of 0.920-0.926 versus 0.900-0.908, the area under the precision-recall curve values of 0.522-0.532 versus 0.485-0.513, and F2 scores of 0.595-0.601 versus 0.385-0.426. Logistic regression or logistic regression hybrid models had higher sensitivity than XGBoost or XGBoost hybrid models (0.837-0.857 vs 0.704-0.735) but a lower positive predictive value (0.122-0.141 vs 0.340-0.367) and specificity (0.793-0.821 vs 0.952-0.958). The hybrid versions of the logistic regression and XGBoost models had slightly higher areas under the precision-recall curve, specificity, and positive predictive values than the respective models that did not include any unsupervised features. Conclusions: XGBoost provided more accurate predictions of measles cases at the county level compared with logistic regression. The threshold of prediction in this model can be adjusted to align with each county’s resources, priorities, and risk for measles. While clustering pattern data from unsupervised machine learning approaches improved some aspects of model performance in this imbalanced data set, the optimal approach for the integration of such approaches with supervised machine learning models requires further investigation.
- Open Access
- 30 March 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Real-World Data Quality Framework for Oncology Time to Treatment Discontinuation Use Case: Implementation and Evaluation Study (Preprint)
BACKGROUND The importance of real-world evidence is widely recognized in observational oncology studies. However, the lack of interoperable data quality standards in the fragmented health information technology landscape represents an important challenge. Therefore, adopting validated systematic methods for evaluating data quality is important for oncology outcomes research leveraging real-world data (RWD). OBJECTIVE This study aims to implement real-world time to treatment discontinuation (rwTTD) for a systemic anticancer therapy (SACT) as a new use case for the Use Case Specific Relevance and Quality Assessment, a framework linking data quality and relevance in fit-for-purpose RWD assessment. METHODS To define the rwTTD use case, we mapped the operational definition of rwTTD to RWD elements commonly available from oncology electronic health record–derived data sets. We identified 20 tasks to check the completeness and plausibility of data elements concerning SACT use, line of therapy (LOT), death date, and length of follow-up. Using descriptive statistics, we illustrated how to implement the Use Case Specific Relevance and Quality Assessment on 2 oncology databases (Data sets A and B) to estimate the rwTTD of an SACT drug (target SACT) for patients with advanced head and neck cancer diagnosed on or after January 1, 2015. RESULTS A total of 1200 (24.96%) of 4808 patients in Data set A and 237 (5.92%) of 4003 patients in Data set B received the target SACT, suggesting better relevance of the former in estimating the rwTTD of the target SACT. The 2 data sets differed with regard to the terminology used for SACT drugs, LOT format, and target SACT LOT distribution over time. Data set B appeared to have less complete SACT records, longer lags in incorporating the latest data, and incomplete mortality data, suggesting a lack of fitness for estimating rwTTD. CONCLUSIONS The fit-for-purpose data quality assessment demonstrated substantial variability in the quality of the 2 real-world data sets. The data quality specifications applied for rwTTD estimation can be expanded to support a broad spectrum of oncology use cases.
- 30 March 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessReal-World Data Quality Framework for Oncology Time to Treatment Discontinuation Use Case: Implementation and Evaluation Study (Preprint)
BACKGROUND The importance of real-world evidence is widely recognized in observational oncology studies. However, the lack of interoperable data quality standards in the fragmented health information technology landscape represents an important challenge. Therefore, adopting validated systematic methods for evaluating data quality is important for oncology outcomes research leveraging real-world data (RWD). OBJECTIVE This study aims to implement real-world time to treatment discontinuation (rwTTD) for a systemic anticancer therapy (SACT) as a new use case for the Use Case Specific Relevance and Quality Assessment, a framework linking data quality and relevance in fit-for-purpose RWD assessment. METHODS To define the rwTTD use case, we mapped the operational definition of rwTTD to RWD elements commonly available from oncology electronic health record–derived data sets. We identified 20 tasks to check the completeness and plausibility of data elements concerning SACT use, line of therapy (LOT), death date, and length of follow-up. Using descriptive statistics, we illustrated how to implement the Use Case Specific Relevance and Quality Assessment on 2 oncology databases (Data sets A and B) to estimate the rwTTD of an SACT drug (target SACT) for patients with advanced head and neck cancer diagnosed on or after January 1, 2015. RESULTS A total of 1200 (24.96%) of 4808 patients in Data set A and 237 (5.92%) of 4003 patients in Data set B received the target SACT, suggesting better relevance of the former in estimating the rwTTD of the target SACT. The 2 data sets differed with regard to the terminology used for SACT drugs, LOT format, and target SACT LOT distribution over time. Data set B appeared to have less complete SACT records, longer lags in incorporating the latest data, and incomplete mortality data, suggesting a lack of fitness for estimating rwTTD. CONCLUSIONS The fit-for-purpose data quality assessment demonstrated substantial variability in the quality of the 2 real-world data sets. The data quality specifications applied for rwTTD estimation can be expanded to support a broad spectrum of oncology use cases.
- Open Access
- 20 September 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Predicting Measles Outbreaks in the United States: Evaluation of Machine Learning Approaches (Preprint)
BACKGROUND Measles, a highly contagious viral infection, is resurging in the United States, driven by international importation and declining domestic vaccination coverage. Despite this resurgence, measles outbreaks are still rare events that are difficult to predict. Improved methods to predict outbreaks at the county level would facilitate the optimal allocation of public health resources. OBJECTIVE We aimed to validate and compare extreme gradient boosting (XGBoost) and logistic regression, 2 supervised learning approaches, to predict the US counties most likely to experience measles cases. We also aimed to assess the performance of hybrid versions of these models that incorporated additional predictors generated by 2 clustering algorithms, hierarchical density-based spatial clustering of applications with noise (HDBSCAN) and unsupervised random forest (uRF). METHODS We constructed a supervised machine learning model based on XGBoost and unsupervised models based on HDBSCAN and uRF. The unsupervised models were used to investigate clustering patterns among counties with measles outbreaks; these clustering data were also incorporated into hybrid XGBoost models as additional input variables. The machine learning models were then compared to logistic regression models with and without input from the unsupervised models. RESULTS Both HDBSCAN and uRF identified clusters that included a high percentage of counties with measles outbreaks. XGBoost and XGBoost hybrid models outperformed logistic regression and logistic regression hybrid models, with the area under the receiver operating curve values of 0.920-0.926 versus 0.900-0.908, the area under the precision-recall curve values of 0.522-0.532 versus 0.485-0.513, and F2 scores of 0.595-0.601 versus 0.385-0.426. Logistic regression or logistic regression hybrid models had higher sensitivity than XGBoost or XGBoost hybrid models (0.837-0.857 vs 0.704-0.735) but a lower positive predictive value (0.122-0.141 vs 0.340-0.367) and specificity (0.793-0.821 vs 0.952-0.958). The hybrid versions of the logistic regression and XGBoost models had slightly higher areas under the precision-recall curve, specificity, and positive predictive values than the respective models that did not include any unsupervised features. CONCLUSIONS XGBoost provided more accurate predictions of measles cases at the county level compared with logistic regression. The threshold of prediction in this model can be adjusted to align with each county’s resources, priorities, and risk for measles. While clustering pattern data from unsupervised machine learning approaches improved some aspects of model performance in this imbalanced data set, the optimal approach for the integration of such approaches with supervised machine learning models requires further investigation.
- 20 September 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessPredicting Measles Outbreaks in the United States: Evaluation of Machine Learning Approaches (Preprint)
BACKGROUND Measles, a highly contagious viral infection, is resurging in the United States, driven by international importation and declining domestic vaccination coverage. Despite this resurgence, measles outbreaks are still rare events that are difficult to predict. Improved methods to predict outbreaks at the county level would facilitate the optimal allocation of public health resources. OBJECTIVE We aimed to validate and compare extreme gradient boosting (XGBoost) and logistic regression, 2 supervised learning approaches, to predict the US counties most likely to experience measles cases. We also aimed to assess the performance of hybrid versions of these models that incorporated additional predictors generated by 2 clustering algorithms, hierarchical density-based spatial clustering of applications with noise (HDBSCAN) and unsupervised random forest (uRF). METHODS We constructed a supervised machine learning model based on XGBoost and unsupervised models based on HDBSCAN and uRF. The unsupervised models were used to investigate clustering patterns among counties with measles outbreaks; these clustering data were also incorporated into hybrid XGBoost models as additional input variables. The machine learning models were then compared to logistic regression models with and without input from the unsupervised models. RESULTS Both HDBSCAN and uRF identified clusters that included a high percentage of counties with measles outbreaks. XGBoost and XGBoost hybrid models outperformed logistic regression and logistic regression hybrid models, with the area under the receiver operating curve values of 0.920-0.926 versus 0.900-0.908, the area under the precision-recall curve values of 0.522-0.532 versus 0.485-0.513, and F2 scores of 0.595-0.601 versus 0.385-0.426. Logistic regression or logistic regression hybrid models had higher sensitivity than XGBoost or XGBoost hybrid models (0.837-0.857 vs 0.704-0.735) but a lower positive predictive value (0.122-0.141 vs 0.340-0.367) and specificity (0.793-0.821 vs 0.952-0.958). The hybrid versions of the logistic regression and XGBoost models had slightly higher areas under the precision-recall curve, specificity, and positive predictive values than the respective models that did not include any unsupervised features. CONCLUSIONS XGBoost provided more accurate predictions of measles cases at the county level compared with logistic regression. The threshold of prediction in this model can be adjusted to align with each county’s resources, priorities, and risk for measles. While clustering pattern data from unsupervised machine learning approaches improved some aspects of model performance in this imbalanced data set, the optimal approach for the integration of such approaches with supervised machine learning models requires further investigation.
- Open Access
- 19 September 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Comparison of Machine Learning Algorithms for Predicting Hospital Readmissions and Worsening Heart Failure Events in Patients With Heart Failure With Reduced Ejection Fraction: Modeling Study (Preprint)
BACKGROUND Heart failure (HF) is highly prevalent in the United States. Approximately one-third to one-half of HF cases are categorized as HF with reduced ejection fraction (HFrEF). Patients with HFrEF are at risk of worsening HF, have a high risk of adverse outcomes, and experience higher health care use and costs. Therefore, it is crucial to identify patients with HFrEF who are at high risk of subsequent events after HF hospitalization. OBJECTIVE Machine learning (ML) has been used to predict HF-related outcomes. The objective of this study was to compare different ML prediction models and feature construction methods to predict 30-, 90-, and 365-day hospital readmissions and worsening HF events (WHFEs). METHODS We used the Veradigm PINNACLE outpatient registry linked to Symphony Health’s Integrated Dataverse data from July 1, 2013, to September 30, 2017. Adults with a confirmed diagnosis of HFrEF and HF-related hospitalization were included. WHFEs were defined as HF-related hospitalizations or outpatient intravenous diuretic use within 1 year of the first HF hospitalization. We used different approaches to construct ML features from clinical codes, including frequencies of clinical classification software (CCS) categories, Bidirectional Encoder Representations From Transformers (BERT) trained with CCS sequences (BERT + CCS), BERT trained on raw clinical codes (BERT + raw), and prespecified features based on clinical knowledge. A multilayer perceptron neural network, extreme gradient boosting (XGBoost), random forest, and logistic regression prediction models were applied and compared. RESULTS A total of 30,687 adult patients with HFrEF were included in the analysis; 11.41% (3184/27,917) of adults experienced a hospital readmission within 30 days of their first HF hospitalization, and nearly half (9231/21,562, 42.81%) of the patients experienced at least 1 WHFE within 1 year after HF hospitalization. The prediction models and feature combinations with the best area under the receiver operating characteristic curve (AUC) for each outcome were XGBoost with CCS frequency (AUC=0.595) for 30-day readmission, random forest with CCS frequency (AUC=0.630) for 90-day readmission, XGBoost with CCS frequency (AUC=0.649) for 365-day readmission, and XGBoost with CCS frequency (AUC=0.640) for WHFEs. Our ML models could discriminate between readmission and WHFE among patients with HFrEF. Our model performance was mediocre, especially for the 30-day readmission events, most likely owing to limitations of the data, including an imbalance between positive and negative cases and high missing rates of many clinical variables and outcome definitions. CONCLUSIONS We predicted readmissions and WHFEs after HF hospitalizations in patients with HFrEF. Features identified by data-driven approaches may be comparable with those identified by clinical domain knowledge. Future work may be warranted to validate and improve the models using more longitudinal electronic health records that are complete, are comprehensive, and have a longer follow-up time.
- 19 September 2022
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessComparison of Machine Learning Algorithms for Predicting Hospital Readmissions and Worsening Heart Failure Events in Patients With Heart Failure With Reduced Ejection Fraction: Modeling Study (Preprint)
BACKGROUND Heart failure (HF) is highly prevalent in the United States. Approximately one-third to one-half of HF cases are categorized as HF with reduced ejection fraction (HFrEF). Patients with HFrEF are at risk of worsening HF, have a high risk of adverse outcomes, and experience higher health care use and costs. Therefore, it is crucial to identify patients with HFrEF who are at high risk of subsequent events after HF hospitalization. OBJECTIVE Machine learning (ML) has been used to predict HF-related outcomes. The objective of this study was to compare different ML prediction models and feature construction methods to predict 30-, 90-, and 365-day hospital readmissions and worsening HF events (WHFEs). METHODS We used the Veradigm PINNACLE outpatient registry linked to Symphony Health’s Integrated Dataverse data from July 1, 2013, to September 30, 2017. Adults with a confirmed diagnosis of HFrEF and HF-related hospitalization were included. WHFEs were defined as HF-related hospitalizations or outpatient intravenous diuretic use within 1 year of the first HF hospitalization. We used different approaches to construct ML features from clinical codes, including frequencies of clinical classification software (CCS) categories, Bidirectional Encoder Representations From Transformers (BERT) trained with CCS sequences (BERT + CCS), BERT trained on raw clinical codes (BERT + raw), and prespecified features based on clinical knowledge. A multilayer perceptron neural network, extreme gradient boosting (XGBoost), random forest, and logistic regression prediction models were applied and compared. RESULTS A total of 30,687 adult patients with HFrEF were included in the analysis; 11.41% (3184/27,917) of adults experienced a hospital readmission within 30 days of their first HF hospitalization, and nearly half (9231/21,562, 42.81%) of the patients experienced at least 1 WHFE within 1 year after HF hospitalization. The prediction models and feature combinations with the best area under the receiver operating characteristic curve (AUC) for each outcome were XGBoost with CCS frequency (AUC=0.595) for 30-day readmission, random forest with CCS frequency (AUC=0.630) for 90-day readmission, XGBoost with CCS frequency (AUC=0.649) for 365-day readmission, and XGBoost with CCS frequency (AUC=0.640) for WHFEs. Our ML models could discriminate between readmission and WHFE among patients with HFrEF. Our model performance was mediocre, especially for the 30-day readmission events, most likely owing to limitations of the data, including an imbalance between positive and negative cases and high missing rates of many clinical variables and outcome definitions. CONCLUSIONS We predicted readmissions and WHFEs after HF hospitalizations in patients with HFrEF. Features identified by data-driven approaches may be comparable with those identified by clinical domain knowledge. Future work may be warranted to validate and improve the models using more longitudinal electronic health records that are complete, are comprehensive, and have a longer follow-up time.
- Open Access
Generic medical concept embedding and time decay for diverse patient outcome prediction tasks
- Open Access
- 1 November 2021
- Published by Oxford University Press (OUP) in Open Forum Infectious Diseases
- Vol. 8 (Supplement) , S759
1344. Predicting Measles Outbreaks in the United States: Application of Different Modeling Approaches
Although measles is still rare in the United States (U.S.), there have been recent resurgent outbreaks in the U.S. To improve the accuracy of prediction given the rarity of measles events, we used machine learning (ML) algorithms to model measles case predictions at the U.S. county level. The main outcome was occurrence of ≥1 measles case at the U.S. county level. Two ML prediction models were developed (HDBSCAN, a clustering algorithm, and XGBoost, a gradient boosting algorithm) and compared with traditional logistic regression. We included 28 predictors in the following categories: sociodemographics, population statistics, measles vaccination coverage, healthcare access, and exposure to measles via international air travel. The models were trained on 2014 case data and validated on 2018 case data. Models were compared using area under the receiver operating curve (AUC), sensitivity, specificity, positive predictive value (PPV), and F2 score (combined measure of sensitivity and PPV). There were 667 measles cases in 2014 and 375 in 2018 in the U.S. We identified U.S. counties for 635 (95.2%) cases in 2014 and 366 (97.6%) cases in 2018 through published sources, corresponding to 81/3143 (2.6%) counties in 2014 and 64/3143 (2.0%) counties in 2018 with ≥1 measles case. HDBSCAN had the highest sensitivity (0.92), but lowest AUC (0.68) and PPV (0.04) (Table). XGBoost had the highest F2 score (0.49), best balance of sensitivity (0.72) and specificity (0.94), and AUC = 0.92. Logistic regression had high AUC (0.91) and specificity (1.00) but the lowest sensitivity (0.16). Machine learning approaches outperformed logistic regression by maximizing sensitivity to predict counties with measles cases, an important criterion to consider to prevent or prepare for future outbreaks. XGBoost or logistic regression could be considered to maximize specificity. Prioritizing sensitivity versus specificity may depend on county resources, priorities, and measles risk. Different modeling approaches could be considered to optimize surveillance efforts and develop effective interventions for timely response. Stephanie Kujawski, PhD MPH, Merck & Co., Inc. (Employee, Shareholder) Boshu Ru, Ph.D., Merck & Co. Kenilworth, NJ (NYSE: MRK) (Employee, Shareholder) Amar K. Das, MD, PhD, Merck (Employee) richard baumgartner, PhD, Merck (Employee) Shuang Lu, MBA, MS, Merck (Employee) Matthew Pillsbury, PhD, Merck & CO. (Employee, Shareholder) Joseph Lewnard, PhD, Merck (Consultant, Grant/Research Support) James H. Conway, MD, FAAP, GSK (Advisor or Review Panel member)Merck (Advisor or Review Panel member)Moderna (Advisor or Review Panel member)Pfizer (Advisor or Review Panel member)Sanofi Pasteur (Research Grant or Support) Manjiri D. Pawaskar, PhD, Merck & Co., Inc. (Employee, Shareholder)
- 1 November 2021
- Published by Oxford University Press (OUP) in Open Forum Infectious Diseases
- Vol. 8 (Supplement) , S759
Open Access1344. Predicting Measles Outbreaks in the United States: Application of Different Modeling Approaches
Although measles is still rare in the United States (U.S.), there have been recent resurgent outbreaks in the U.S. To improve the accuracy of prediction given the rarity of measles events, we used machine learning (ML) algorithms to model measles case predictions at the U.S. county level. The main outcome was occurrence of ≥1 measles case at the U.S. county level. Two ML prediction models were developed (HDBSCAN, a clustering algorithm, and XGBoost, a gradient boosting algorithm) and compared with traditional logistic regression. We included 28 predictors in the following categories: sociodemographics, population statistics, measles vaccination coverage, healthcare access, and exposure to measles via international air travel. The models were trained on 2014 case data and validated on 2018 case data. Models were compared using area under the receiver operating curve (AUC), sensitivity, specificity, positive predictive value (PPV), and F2 score (combined measure of sensitivity and PPV). There were 667 measles cases in 2014 and 375 in 2018 in the U.S. We identified U.S. counties for 635 (95.2%) cases in 2014 and 366 (97.6%) cases in 2018 through published sources, corresponding to 81/3143 (2.6%) counties in 2014 and 64/3143 (2.0%) counties in 2018 with ≥1 measles case. HDBSCAN had the highest sensitivity (0.92), but lowest AUC (0.68) and PPV (0.04) (Table). XGBoost had the highest F2 score (0.49), best balance of sensitivity (0.72) and specificity (0.94), and AUC = 0.92. Logistic regression had high AUC (0.91) and specificity (1.00) but the lowest sensitivity (0.16). Machine learning approaches outperformed logistic regression by maximizing sensitivity to predict counties with measles cases, an important criterion to consider to prevent or prepare for future outbreaks. XGBoost or logistic regression could be considered to maximize specificity. Prioritizing sensitivity versus specificity may depend on county resources, priorities, and measles risk. Different modeling approaches could be considered to optimize surveillance efforts and develop effective interventions for timely response. Stephanie Kujawski, PhD MPH, Merck & Co., Inc. (Employee, Shareholder) Boshu Ru, Ph.D., Merck & Co. Kenilworth, NJ (NYSE: MRK) (Employee, Shareholder) Amar K. Das, MD, PhD, Merck (Employee) richard baumgartner, PhD, Merck (Employee) Shuang Lu, MBA, MS, Merck (Employee) Matthew Pillsbury, PhD, Merck & CO. (Employee, Shareholder) Joseph Lewnard, PhD, Merck (Consultant, Grant/Research Support) James H. Conway, MD, FAAP, GSK (Advisor or Review Panel member)Merck (Advisor or Review Panel member)Moderna (Advisor or Review Panel member)Pfizer (Advisor or Review Panel member)Sanofi Pasteur (Research Grant or Support) Manjiri D. Pawaskar, PhD, Merck & Co., Inc. (Employee, Shareholder)
- Open Access
- 1 July 2021
- Published by The Journal of Health Economics and Outcomes Research in Journal of Health Economics and Outcomes Research
- Vol. 8 (2) , 6-13
Using Deep Learning to Identify High-Risk Patients with Heart Failure with Reduced Ejection Fraction
Background: Deep Learning (DL) has not been well-established as a method to identify high-risk patients among patients with heart failure (HF). Objectives: This study aimed to use DL models to predict hospitalizations, worsening HF events, and 30-day and 90-day readmissions in patients with heart failure with reduced ejection fraction (HFrEF). Methods: We analyzed the data of adult HFrEF patients from the IBM® MarketScan® Commercial and Medicare Supplement databases between January 1, 2015 and December 31, 2017. A sequential model architecture based on bi-directional long short-term memory (Bi-LSTM) layers was utilized. For DL models to predict HF hospitalizations and worsening HF events, we utilized two study designs: with and without a buffer window. For comparison, we also tested multiple traditional machine learning models including logistic regression, random forest, and eXtreme Gradient Boosting (XGBoost). Model performance was assessed by area under the curve (AUC) values, precision, and recall on an independent testing dataset. Results: A total of 47 498 HFrEF patients were included; 9427 with at least one HF hospitalization. The best AUCs of DL models without a buffer window in predicting HF hospitalizations and worsening HF events in the total patient cohort were 0.977 and 0.972; with a 7-day buffer window the best AUCs were 0.573 and 0.608, respectively. The best AUCs in predicting 30- and 90-day readmissions in all adult patients were 0.597 and 0.614, respectively. An AUC of 0.861 was attained for prediction of 90-day readmission in patients aged 18-64. For all outcomes assessed, the DL approach outperformed traditional machine learning models. Discussion: The DL approach can automate feature engineering during the model learning, which can increase the clinical applicability and lead to comparable or better model performance. However, the lack of granular clinical data, and sample size and imbalance issues may have limited the model’s performance. Conclusions: A DL approach using Bi-LSTM was shown to be a feasible and useful tool to predict HF-related outcomes. This study can help inform the future development and deployment of predictive tools to identify high-risk HFrEF patients and ultimately facilitate targeted interventions in clinical practice.
- 1 July 2021
- Published by The Journal of Health Economics and Outcomes Research in Journal of Health Economics and Outcomes Research
- Vol. 8 (2) , 6-13
Open AccessUsing Deep Learning to Identify High-Risk Patients with Heart Failure with Reduced Ejection Fraction
Background: Deep Learning (DL) has not been well-established as a method to identify high-risk patients among patients with heart failure (HF). Objectives: This study aimed to use DL models to predict hospitalizations, worsening HF events, and 30-day and 90-day readmissions in patients with heart failure with reduced ejection fraction (HFrEF). Methods: We analyzed the data of adult HFrEF patients from the IBM® MarketScan® Commercial and Medicare Supplement databases between January 1, 2015 and December 31, 2017. A sequential model architecture based on bi-directional long short-term memory (Bi-LSTM) layers was utilized. For DL models to predict HF hospitalizations and worsening HF events, we utilized two study designs: with and without a buffer window. For comparison, we also tested multiple traditional machine learning models including logistic regression, random forest, and eXtreme Gradient Boosting (XGBoost). Model performance was assessed by area under the curve (AUC) values, precision, and recall on an independent testing dataset. Results: A total of 47 498 HFrEF patients were included; 9427 with at least one HF hospitalization. The best AUCs of DL models without a buffer window in predicting HF hospitalizations and worsening HF events in the total patient cohort were 0.977 and 0.972; with a 7-day buffer window the best AUCs were 0.573 and 0.608, respectively. The best AUCs in predicting 30- and 90-day readmissions in all adult patients were 0.597 and 0.614, respectively. An AUC of 0.861 was attained for prediction of 90-day readmission in patients aged 18-64. For all outcomes assessed, the DL approach outperformed traditional machine learning models. Discussion: The DL approach can automate feature engineering during the model learning, which can increase the clinical applicability and lead to comparable or better model performance. However, the lack of granular clinical data, and sample size and imbalance issues may have limited the model’s performance. Conclusions: A DL approach using Bi-LSTM was shown to be a feasible and useful tool to predict HF-related outcomes. This study can help inform the future development and deployment of predictive tools to identify high-risk HFrEF patients and ultimately facilitate targeted interventions in clinical practice.